Abstract | ||
---|---|---|
More and more work has focused on incorporating different kinds of literals into Knowledge Graph to promote the performance of knowledge embedding. These literals contain numeric literals, text literals, image literals and so on. These additional descriptions are connected to the entities through certain attributes. To incorporate numeric literals, some methods combine the embeddings of literals part with the traditional part - embeddings of entities. However, in the construction of literals embeddings, these existing methods consider the differences of these attributes: one dimension represents one attribute. But they ignore semantic meanings of attributes themselves. In this paper, we propose two methods to incorporate attributes semantics into knowledge graph embeddings from two perspectives: LiteralE-AN and literalE-AT. They concatenate with the embeddings of numeric literals by different ways. Furthermore, their extension model LiteralE-C is also proposed as having a more comprehensive representation of attributes semantics. In an empirical study over two standard datasets FB15k and FB15k-237, we evaluate our models for link prediction. We demonstrate that they show an effective way to improve LiteralE and achieve state-of-the-art results. In ablation experiments, we find c ombined m odels do better than their singular counterparts in most cases. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CSCWD49262.2021.9437876 | PROCEEDINGS OF THE 2021 IEEE 24TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN (CSCWD) |
Keywords | DocType | Citations |
knowledge representation learning, numeric literals, attributes semantics, link prediction | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mingyang Li | 1 | 0 | 0.68 |
Neng Gao | 2 | 1 | 6.44 |
Chenyang Tu | 3 | 0 | 6.08 |
Peng Jia | 4 | 87 | 23.41 |
Min Li | 5 | 0 | 1.35 |